Tobias Goerke
Tobias Goerke
The complexity of constructing anchors mainly depends on the number of features. Thus, if an instance has many features, the algorithm is slow. The parameter maxAnchorSize allows to constrain the...
Anchors is able to explain any model's decision (e.g. for a label it predicted). However, the explained label does not necessarily have to equal the value the model did actually...
### Environment * KFP version: `2.0.3` (manifests v1.8 release) * KFP SDK version: ``` kfp 2.4.0 kfp-kubernetes 1.0.0 kfp-pipeline-spec 0.2.2 kfp-server-api 2.0.3 ``` Issue is possibly related to https://github.com/kubeflow/pipelines/issues/9386. ###...
The application would greatly benefit from utilizing multiple threads. For R, this is no easy task and comes with plenty overhead. However, there are multiple options we should think about....
I'd like to see the printExplanations only require the explainer's outcome, not also the explainer instance itself. This would make handling the API much easier. After all, plotExplanations only requires...
I'd like to see a functionality with which the user can define custom perturbation spaces. This would also solve #37 and we could offer two API options: + Either provide...
Why does a train set need to be passed to anchors()? Anchors is able to run without a data set. Just the default perturbation should require a dataset
The current perturbation generation function is in need of performance improvement. Generating all perturbations that were asked for at once would help to reduce the total runtime.